a29b4e23fd* fix(studio): reuse HF cached repo casing to prevent duplicate downloads * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Move cache case resolution tests to separate PR Tests for resolve_cached_repo_id_case and get_model_config case resolution belong in their own PR to keep this change focused on the runtime fix. * fix(studio): debug-log HF_HUB_CACHE fallback in path_utils * Fix stale memoization in resolve_cached_repo_id_case - Check exact-case path before memo to ensure a newly-appeared exact match always wins over a previously memoized variant - Validate memoized entries still exist on disk before returning them to prevent stale results when cache dirs are deleted/recreated * Minor cleanups for cache case resolution - Use .is_dir() instead of .exists() for exact-case cache check (cache entries are always directories) - Remove redundant fallback in _detect_audio_from_tokenizer since get_cache_path already handles case resolution and returns None when the model is not cached --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com>
80 lines
1.9 KiB
Python
80 lines
1.9 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""
|
|
Path utilities for model and dataset handling
|
|
"""
|
|
|
|
from .path_utils import (
|
|
normalize_path,
|
|
is_local_path,
|
|
is_model_cached,
|
|
get_cache_path,
|
|
resolve_cached_repo_id_case,
|
|
get_cache_case_resolution_stats,
|
|
reset_cache_case_resolution_state,
|
|
)
|
|
from .storage_roots import (
|
|
studio_root,
|
|
assets_root,
|
|
datasets_root,
|
|
dataset_uploads_root,
|
|
recipe_datasets_root,
|
|
outputs_root,
|
|
exports_root,
|
|
auth_root,
|
|
auth_db_path,
|
|
studio_db_path,
|
|
tmp_root,
|
|
seed_uploads_root,
|
|
unstructured_seed_cache_root,
|
|
unstructured_uploads_root,
|
|
oxc_validator_tmp_root,
|
|
tensorboard_root,
|
|
legacy_hf_cache_dir,
|
|
hf_default_cache_dir,
|
|
lmstudio_model_dirs,
|
|
ensure_dir,
|
|
ensure_studio_directories,
|
|
resolve_under_root,
|
|
resolve_output_dir,
|
|
resolve_export_dir,
|
|
resolve_tensorboard_dir,
|
|
resolve_dataset_path,
|
|
)
|
|
|
|
__all__ = [
|
|
"normalize_path",
|
|
"is_local_path",
|
|
"is_model_cached",
|
|
"get_cache_path",
|
|
"resolve_cached_repo_id_case",
|
|
"get_cache_case_resolution_stats",
|
|
"reset_cache_case_resolution_state",
|
|
"studio_root",
|
|
"assets_root",
|
|
"datasets_root",
|
|
"dataset_uploads_root",
|
|
"recipe_datasets_root",
|
|
"outputs_root",
|
|
"exports_root",
|
|
"auth_root",
|
|
"auth_db_path",
|
|
"studio_db_path",
|
|
"tmp_root",
|
|
"seed_uploads_root",
|
|
"unstructured_seed_cache_root",
|
|
"unstructured_uploads_root",
|
|
"oxc_validator_tmp_root",
|
|
"tensorboard_root",
|
|
"legacy_hf_cache_dir",
|
|
"hf_default_cache_dir",
|
|
"lmstudio_model_dirs",
|
|
"ensure_dir",
|
|
"ensure_studio_directories",
|
|
"resolve_under_root",
|
|
"resolve_output_dir",
|
|
"resolve_export_dir",
|
|
"resolve_tensorboard_dir",
|
|
"resolve_dataset_path",
|
|
]
|